setup
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses benign inspection commands such as
ls,find, andcatto understand the project structure and documentation layout. These operations are limited to project discovery and are typical for configuration wizards.- [INDIRECT_PROMPT_INJECTION]: The skill evaluates information from local project files (e.g.,README.md,ARCHITECTURE.md) to guide the setup process. This constitutes a data ingestion surface where external content enters the agent context. - Ingestion points: File discovery and reading in Phase 1 and Phase 2.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the scripts.
- Capability inventory: The skill utilizes
Read,Bash,Glob,Grep,Write, andEdittools. - Sanitization: No explicit sanitization or validation of the ingested file content is performed.
Audit Metadata